John Hartman
Software Developer For SHMEM at Hewlett Packard Enterprise
Tucson, Arizona, United States
Summary
🤩
Rockstar🎓
Top SchoolJohn Hartman is a seasoned software developer and systems researcher with 10+ years of practical engineering experience and a decades-long academic pedigree culminating in a Ph.D. from UC Berkeley. He has deep expertise in distributed and parallel runtime systems, having driven Chapel runtime enhancements (including Libfabric upgrades, PMI2 support, and oversubscription detection) and now focuses on SHMEM development at Hewlett Packard Enterprise. His background spans industry and academia—from cofounding a startup and designing DNS-based CDN routing to consulting at Akamai and teaching systems research as an associate professor—giving him a rare blend of product, operational, and research perspectives. He is based in Tucson, Arizona, and brings hands-on low-level networking and communication-layer skill with a history of contributing to a well-known parallel programming language ecosystem. Notably, his Chapel work added options for message injection and core dedication for active-message handlers, reflecting a pragmatic approach to performance and operability.
11 years of coding experience
31 years of employment as a software developer
Doctor of Philosophy (Ph.D.) Computer Science, Doctor of Philosophy (Ph.D.) Computer Science at University of California, BerkeleySc.B. Computer Science, Sc.B. Computer Science at Brown University
Github Skills (17)
chapel10
performance-monitor9
performance-analytics9
performance-measurement9
mpi9
performance-monitoring9
performance-analysis9
performance-tuning9
concurrency8
parallel-computing8
hpc8
buildr7
devops7
build-engine7
automation7
Programming languages (5)
Github contributions (5)
chapel-lang/chapel
Jul 2021 - Jan 2023
a Productive Parallel Programming Language
Role in this project:
Back-end Developer
Back-end DeveloperContributions:347 reviews, 166 commits, 442 PRs in 1 year 6 months
Contributions summary:John primarily contributed to the Chapel runtime environment, focusing on improving the communication layer. Their work includes adding features for determining oversubscription via the number of locales on a node and implementing the `chpl_comm_ofi_oob_locales_on_node` function for PMI2. They also updated the Libfabric library to version 1.12.1 and later 1.13.2, along with fixing issues related to the providers. Furthermore, the user introduced the option to inject messages and to dedicate cores to AM handlers.
programming-languagecompilergpuhpcparallel
jhh67/chapel
Jun 2021 - Jul 2025
a Productive Parallel Programming Language
Contributions:2615 pushes, 529 branches, 9 tags in 4 years 1 month
aplfmiparallellanguage-designproductive
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.